JP2018196428A - Rough skin evaluation method and rough skin evaluation device - Google Patents

Abstract

To provide a technique to quantify an impression of rough skin from its appearance.SOLUTION: A rough skin evaluation method has a step (S11) for acquiring a desquamation ratio which is a ratio of the area of a desquamation region extracted from a skin image of a subject, to the skin area of the skin image, and a step (S12) for quantifying the rough skin conditions by changing indices or methods depending on whether the desquamation ratio acquired in the step (S11) is more than or less than a predetermined ratio.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a skin image analysis technique.

In Patent Document 1, a still image of skin is divided into minute regions, the image is binarized by a threshold value determined for each minute region, and the ratio of the area in the entire region of the region where dry desquamation changes occur is determined as the skin roughness rate A method of quantifying as is disclosed.
In Patent Document 2, the stratum corneum on the skin surface is attached to the adhesive surface of the stratum corneum collection sheet, and the amount of peel and uniformity of the exfoliated stratum corneum adhering to the sheet are objectively quantified. A method for evaluating the state of the stratum corneum has been proposed.
In Patent Document 3, a large number of stratum corneum images are acquired from a large number of subjects by a method in which stratum corneum is attached to an adhesive transparent tape and the tape is imaged with a camera, and the acquired large number of stratum corneum images are regarded as determination targets. Based on the stratum corneum image of a test subject, a method for generating a skin condition determination map with two indexes of the stratum corneum layering degree and the rough skin degree as two axes has been proposed.

Japanese Patent Publication No. 6-14908 JP 9-131323 A JP 2003-28856 A

Each of the above methods leaves room for various improvements in quantifying the appearance of rough skin. For example, in the methods disclosed in Patent Documents 2 and 3, it is necessary to peel the stratum corneum from the skin surface with an adhesive tape or a collection sheet, and the state of the peeled stratum is only evaluated. Moreover, in the method disclosed in Patent Document 1, the ratio of the area of the entire region where the dry desquamability change occurs is merely used as the skin roughness rate, and the appearance impression of the skin roughness is accurately quantified. It is not necessarily possible.
In view of such circumstances, the present invention provides a technique for quantifying the appearance of rough skin.
In this specification, “rough skin” broadly means a skin condition accompanied by desquamation, and can also be expressed as a skin dry condition, a skin desquamation condition, or the like.
“Desquamation” means a state in which keratin is being peeled off from the skin surface or a state in which it is peeled off and adheres to the skin surface, and includes the meaning of scales.

  Each aspect of the present invention employs the following configurations in order to solve the above-described problems.

  A 1st aspect is related with the rough skin evaluation method. The skin roughness evaluation method according to the first aspect includes a step of obtaining a desquamation ratio that is a ratio of an area of a desquamation area extracted from the skin image to a skin area of a subject's skin image, and the obtained desquamation ratio is predetermined. Quantifying the rough skin condition using a different index or a different method depending on whether the ratio is lower or higher.

  A 2nd aspect is related with the rough skin evaluation apparatus. In the rough skin evaluation apparatus according to the second aspect, an acquisition unit that acquires a desquamation ratio that is a ratio of an area of a desquamation region extracted from the skin image to a skin area of the skin image of the subject, and the acquired desquamation ratio is Quantifying means for quantifying the rough skin condition using a different index or a different method depending on whether the ratio is lower or higher than the predetermined ratio.

  As another aspect of the present invention, a program that causes a computer to execute the rough skin evaluation method according to the first aspect described above may be used, or a computer-readable storage medium that records such a program may be used. Good. This recording medium includes a non-transitory tangible medium.

  According to each aspect described above, it is possible to provide a technique for quantifying the appearance of rough skin.

It is a flowchart which shows the outline | summary of the rough skin evaluation method. It is a figure which shows notionally the hardware structural example of a rough skin evaluation apparatus. It is a figure which shows notionally the process structural example of a rough skin evaluation apparatus. It is a conceptual diagram which shows the hardware constitutions of the skin diagnostic system which concerns on this embodiment. It is a flowchart which shows the rough skin evaluation method which concerns on this embodiment. It is a figure which shows the example of the island determination rule of an island labeling process. It is a figure which shows an example of an island labeling process. It is a flowchart which shows the detail of a rough skin evaluation determination step. It is a flowchart which shows the 1st modification of a rough skin evaluation determination step. It is a flowchart which shows the 2nd modification of a rough skin evaluation determination step. It is a graph which shows the correlation with the dispersion value of the area of a desquamation area | region, and a desquamation visual score. It is a graph which shows the correlation with the variation coefficient of the area of a desquamation area | region, and desquamation visual score. It is a graph which shows the correlation with the value which multiplied the variance value of the area of a desquamation area | region, and the average area of a desquamation area | region, and a desquamation visual score. It is a graph which shows the correlation with the value which multiplied the dispersion value of the area of a desquamation area | region, and the desquamation ratio, and a desquamation visual score. It is a graph which shows the correlation with a desquamation ratio and a desquamation visual score. (A) is a graph which shows the correlation with a desquamation visual score and the variance value of the area of a desquamation area | region regarding the sample skin image less than desquamation ratio (ratio) 0.18%, (b) is desquamation ratio (ratio). ) It is a graph showing a correlation between a desquamation visual score and a desquamation rate regarding a sample skin image of less than 0.18%. (A) is a graph which shows the correlation with a desquamation visual score and the dispersion value of the area of a desquamation area | region regarding the sample skin image of desquamation ratio (ratio) 0.18% or more, (b) is desquamation ratio (ratio). ) It is a graph showing a correlation between a desquamation visual score and a desquamation ratio regarding a sample skin image of 0.18% or more.

  Embodiments of the present invention will be described below. In addition, embodiment mentioned below is an illustration and this invention is not limited to the structure of the following embodiment.

First, the outline | summary of the rough skin evaluation method which concerns on embodiment mentioned later is demonstrated using FIG.
FIG. 1 is a flowchart showing an outline of a rough skin evaluation method.
The present inventors considered the overall judgment in view of human cognitive function while examining the relationship between the evaluation value obtained by human subjective evaluation of the “appearance” of the skin and various index values. And I came up with the possibility of making a detailed decision after such an overall decision. By proceeding with the examination based on such a possibility, it was confirmed that the relationship between the subjective evaluation value and the index value changes according to the total amount of desquamation in the entire skin. As a result, the present inventors have conceived that the appearance of rough skin can be appropriately quantified by varying the index value and the evaluation method according to the ratio of the desquamation area to the entire skin (desquamation ratio). .
That is, in the rough skin evaluation method according to the embodiment of the present invention, as shown in FIG. 1, the step (S11) of acquiring the desquamation ratio in the skin image of the subject and the desquamation ratio acquired in the step (S11) are predetermined. A step (S12) of quantifying the rough skin state using a different index or a different method depending on whether the ratio is lower or higher.

Here, the “desquamation ratio” is the ratio of the area of the desquamation area extracted from the skin image to the skin area of the subject's skin image.
The “subject's skin image” is an image obtained by imaging the skin of the part to be evaluated by the subject, and may be an image in which desquamation is reflected. In this skin image, it is desirable that a part of a predetermined size in the subject's skin is represented with a predetermined resolution. By normalizing the skin image in this way, a normalized rough skin index value can be obtained.
For example, the skin image is desirably an image in which the gloss component on the skin surface is weakened. This is because the gloss component is difficult to distinguish from the skin surface desquamation on the skin image. In the example described later, an SP polarized image from which the surface reflected light component is removed is used as the skin image.
“The skin area of the skin image of the subject” indicates the size of the region indicating the skin in the skin image of the subject, and may be the entire region (for example, the total number of pixels) of the skin image, May be a partial region (a part of the number of pixels).
The “desquamation region” is a local region where desquamation occurs in the skin image. A method for extracting a desquamation region from a skin image will be described later. However, for this extraction method, a known method such as a method for detecting an area in which dry desquamability change occurs in Patent Document 1 may be used. For example, a lump of pixels indicating desquamation on the skin image is specified as the desquamation area.
The “area of the desquamation area” indicates the size of the desquamation area in the skin image, and is indicated by using, for example, the number of pixels.

In the step (S11), the desquamation area may be extracted from the skin image of the subject, the skin area and the area of the desquamation area may be acquired from the skin image, and the desquamation ratio may be calculated based on these areas.
Further, when the step (S11) is executed by a computer such as a rough skin evaluation apparatus described later, in the step (S11), the desquamation ratio may be received from another computer by communication, or portable recording. The desquamation ratio may be read from a medium or the like, or the desquamation ratio may be input by the user.

The predetermined ratio used in the step (S12) is determined in advance by analyzing the sample skin image, as will be described later in the section of the embodiment.
In the step of quantifying the rough skin state (S12), different indicators or different methods are used depending on whether the desquamation ratio is lower than the predetermined ratio or higher. In other words, when the desquamation ratio exceeds a predetermined ratio, the rough skin state is quantified using the first index value, or the rough skin state is quantified using the first method. On the other hand, when the desquamation ratio is lower than the predetermined ratio, the rough skin state is quantified using the second index value of the index different from the first index value, or the second method different from the first method is used. The rough skin state is quantified.
As the first index value and the second index value here, for example, an index value related to a desquamation area is used. In the quantification using the first index value or the second index value, the first index value or the second index value may be used as the quantitative value as it is, or from the first index value or the second index value by a predetermined method. The converted evaluation value may be a quantitative value.
In the first method and the second method, for example, different expressions using different index values as parameters or different expressions using the same index value as parameters are used.
Details of indices and methods used for quantifying the rough skin state will be described later.
Although omitted in FIG. 1, when the desquamation ratio is equal to the predetermined ratio, the rough skin state may be quantified by the same method as when it is higher, or the rough skin state may be quantified by the same method as when it is lower.

  As described above, according to the present embodiment, the relationship between the subjective evaluation value of human and the index value found by the present inventors changes according to the total amount of desquamation in the entire skin. Based on the knowledge, it is possible to accurately quantify the appearance of the subject's rough skin appearance.

The rough skin evaluation method described above can be executed by, for example, the rough skin evaluation apparatus illustrated in FIGS. 2 and 3.
FIG. 2 is a diagram conceptually illustrating a hardware configuration example of the rough skin evaluation apparatus 10.
The rough skin evaluation apparatus 10 is a so-called computer, and includes, for example, a CPU (Central Processing Unit) 11, a memory 12, an input / output interface (I / F) 13, a communication unit 14, and the like that are connected to each other via a bus. The number of hardware elements forming the rough skin evaluation apparatus 10 is not limited, and these hardware elements can be collectively referred to as an information processing circuit. Further, the rough skin evaluation apparatus 10 may include hardware elements not shown in FIG. 2, and the hardware configuration is not limited.

The CPU 11 may be configured by an application specific integrated circuit (ASIC), a DSP (Digital Signal Processor), a GPU (Graphics Processing Unit), or the like in addition to a general CPU.
The memory 12 is a RAM (Random Access Memory), a ROM (Read Only Memory), or an auxiliary storage device (such as a hard disk).
The input / output I / F 13 can be connected to user interface devices such as the output device 15 and the input device 16. The output device 15 is at least one of a device such as an LCD (Liquid Crystal Display) or a CRT (Cathode Ray Tube) display, a device that displays a screen corresponding to drawing data processed by the CPU 11, a printing device, and the like. The input device 16 is a device that receives an input of a user operation such as a keyboard and a mouse. The output device 15 and the input device 16 may be integrated and realized as a touch panel.
The communication unit 14 performs communication via a communication network with other computers, exchange of signals with other devices, and the like. A portable recording medium or the like can be connected to the communication unit 14. The communication unit 14 may be connected to a camera (not shown) that captures a skin image of the subject.
Moreover, the rough skin evaluation apparatus 10 may be a device incorporating a camera.

FIG. 3 is a diagram conceptually illustrating a processing configuration example of the rough skin evaluation apparatus 10.
The rough skin evaluation apparatus 10 includes an acquisition unit 21 and a quantification unit 22. These processing modules are software elements, and are realized, for example, by executing a program stored in the memory 12 by the CPU 11. This program is installed from, for example, a portable recording medium such as a CD (Compact Disc) or a memory card or another computer on the network via the input / output I / F 13 or the communication unit 14, and stored in the memory 12. May be.

The acquisition part 21 performs the above-mentioned process (S11). At this time, the acquisition unit 21 can acquire the desquamation ratio from an external computer, device, portable recording medium, or the like via the input / output I / F 13 or the communication unit 14. Moreover, the acquisition part 21 acquires a test subject's skin image from the outside, extracts a desquamation area | region from the skin image, acquires the skin area and the area of a desquamation area | region from the skin image, and sets a desquamation ratio based on these areas. It can also be calculated. Moreover, when the rough skin evaluation apparatus 10 incorporates a camera, the acquisition part 21 may acquire the skin image imaged with the camera.
The quantification part 22 performs the above-mentioned process (S12).
The rough skin evaluation apparatus 10 may cause the output device 15 to output the value quantified by the quantification unit 22 as it is, or may cause the output device 15 to output information converted from the value. In the latter case, the quantification unit 22 holds a relative table for converting the first index value or the second index value into the evaluation value in advance, and by referring to this relative table, the first index value or An evaluation value corresponding to the second index value can also be acquired. Further, the quantification unit 23 may hold a conversion formula in advance instead of the relative table.

Hereinafter, preferred embodiments of the present invention will be illustrated and described in detail.
The skin roughness evaluation method according to the following embodiment is implemented as part of skin diagnosis performed using an image obtained by photographing a skin by executing a software program on the skin diagnosis system 30 shown in FIG. When the rough skin evaluation method according to the present embodiment is executed, the whole or a part of the skin diagnostic system 30 can also be called a rough skin evaluation device.

FIG. 4 is a conceptual diagram showing a hardware configuration of the skin diagnostic system 30 according to the present embodiment.
The skin diagnosis system 30 includes an imaging device 31, a projector 32, an information processing device 33, a touch panel 34, and the like.
The imaging device 31 images a skin surface such as the face of the subject S. The imaging device 31 is provided with an imaging polarization filter 36 for selecting light to be imaged on the plane of polarization.
The projector 32 projects photographing light onto the skin surface such as the face of the subject S. The projector 32 is provided with a projection polarizing filter 37 for selecting a polarization plane of light to be projected onto the subject S.
The information processing device 33 performs various calculations for skin diagnosis using an image of the skin surface photographed by the imaging device 31. The information processing device 33 is a general-purpose computer device such as a personal computer. The information processing device 33 includes an external storage device (memory 12) for storing various programs and captured skin surface images, as illustrated in FIG. 2, and a printer (not shown) for printing diagnosis results. An output device 15) is provided.
The touch panel 34 functions as a display unit that displays a photographed skin surface image, a result of skin diagnosis, and the like, and also serves as an input unit for a user of the skin diagnosis system 30 to input various commands to the information processing device 33. Function. The touch panel 34 corresponds to the output device 15 and the input device 16 in FIG.

  Various known skin diagnoses are executed by starting and executing the program in the information processing apparatus 33 of the skin diagnosis system 30 as described above, and the rough skin evaluation method according to the present embodiment is executed. The information processing device 33 corresponds to the rough skin evaluation device 10 described above.

Hereinafter, the rough skin evaluation method according to the present embodiment will be described with reference to FIG.
FIG. 5 is a flowchart showing the rough skin evaluation method according to the present embodiment.
In the present embodiment, the rough skin evaluation program P0 is executed in the information processing apparatus 33, whereby the rough skin evaluation method as described below is executed.

As shown in FIG. 5, the rough skin evaluation method according to the present embodiment includes a desquamation part extraction step (S51), an island labeling step (S52), an island area calculation step (S53), and a rough skin evaluation determination step (S54). Contains.
Hereinafter, each step for forming the rough skin evaluation method according to the present embodiment will be described in more detail.

In step (S51), a desquamation part is extracted from the skin image obtained by imaging the skin of the subject S.
Specifically, a so-called P-polarized image (also referred to as an SP polarized image) is an image obtained by making the polarization direction of the imaging polarizing filter 36 perpendicular to the polarization direction of the projecting polarizing filter 37 of the projector 32. Is acquired from the imaging device 31 as an original image. This original image is an image from which the surface reflected light component is removed by polarization. A subtraction process is performed between the low-frequency image obtained by applying a low-pass filter (smoothing filter) such as a Gaussian filter to the original image, and a difference image is obtained. The obtained difference image is binarized with a predetermined threshold value, so that a desquamation map image indicating the desquamation position can be obtained. In this desquamation map image, white pixels are regarded as desquamation parts.
However, instead of such an SP polarized image, an ultraviolet skin image captured in an ultraviolet environment may be used as the original image. Moreover, the method for extracting the desquamated portion from the original image may not be limited to the above-described method, and a known method may be used.

In step (S52), island labeling processing is performed in which the continuous desquamating parts in the desquamating part group extracted in step (S51) are formed as one lump. Here, in the above-described desquamation map image, the lump of the desquamation part is specified, and a number is assigned to each lump. Specifically, among the pixels corresponding to the desquamating part, a continuous pixel group is specified as the lump of the desquamating part, and the same number is assigned to the continuous pixel group corresponding to the lump of the desquamating part, which corresponds to the other lump. Different numbers are assigned to consecutive pixel groups.
FIG. 6 is a diagram illustrating an example of an island determination rule for island labeling processing. For example, as in “lumps 1” and “lumps 2” shown in FIG. 6, among the pixels corresponding to the desquamated portion, a group of pixels adjacent in the vertical direction or the horizontal direction is a lump (island) of the desquamated portion. Determined. In the example of FIG. 6, pixels that are adjacent only diagonally are not determined as a lump (island). However, even pixels that are adjacent only diagonally may be determined as a lump (island).
FIG. 7 is a diagram illustrating an example of island labeling processing. In FIG. 7, each square represents a pixel. The upper diagram of FIG. 7 shows a desquamation map image (binarized image). In the example of FIG. 7, it is assumed that black pixels indicate a desquamation part due to restrictions on the drawing. The lower diagram of FIG. 7 is a diagram showing a result of performing the island labeling process on the upper image of FIG. 7, and a unique number is assigned to each pixel for each lump of the desquamated portion. In the example of FIG. 7, twelve chunks (islands) are specified, and twelve unique numbers (hexadecimal notation) are assigned to each chunk.
A specific algorithm for the island labeling process is not particularly limited, and any algorithm can be used.

  In step (S51), a desquamation part is extracted from the skin image, and in step (S52), a continuous pixel group in pixels corresponding to the desquamation part is collected as a lump, and a desquamation area is extracted.

  In step (S53), the island identified in step (S52), that is, the area for each desquamation area is calculated. For example, by counting the number of pixels with the same number, the area for each desquamation area can be obtained. The area for each desquamation area calculated in step (S53) is stored in the desquamation area table on the storage area of the information processing device 33.

In step (S54), a rough skin evaluation value is acquired using information stored in the desquamating area table. In the present embodiment, the rough skin evaluation value is divided into 10 stages, and the rough skin evaluation value is calculated in step (S54) with the worst state being 1 and the best state being 10.
Details of the rough skin evaluation determination step (S54) will be described below with reference to FIG.
FIG. 8 is a flowchart showing details of the rough skin evaluation determination step (S54).

In step (S54), first, the ratio of the total area of the desquamating area to the skin area of the skin image used in step (S51), that is, the desquamation ratio is calculated (step (S81)). In the present embodiment, a series of steps from step (S51) to step (S81) corresponds to the above-described step (S11).
The skin area may be the entire region (for example, the total number of pixels) of the skin image or a partial region (the number of pixels) of the skin image.

Subsequently, in step (S82), the desquamation ratio is compared with a predetermined ratio, and one of step (S83) and steps (S84) and (S85) is executed according to the comparison result. These steps (S82), (S83), (S84), and (S85) are specific examples of the above-described step (S12).
In the present embodiment, as shown in FIG. 8, the predetermined ratio is 0.18%, and different indicators and different formulas are used depending on whether the desquamation ratio is 0.18% or more and less than 0.18%. Is used to quantify the rough skin condition. However, the numerical value of the predetermined ratio is not limited. The predetermined ratio is preferably determined in advance by analysis of the sample skin image. Therefore, the value may vary depending on the selected sample skin image.

Specifically, when the desquamation ratio is equal to or greater than a predetermined ratio (0.18%) (S82; Y), the desquamation ratio evaluation step (S83) is executed, and when the desquamation ratio is less than the predetermined ratio (S82; N). ), The area dispersion value calculation step (S84) and the area dispersion value evaluation step (S85) are executed.
In the desquamation rate evaluation step (S83), a rough skin evaluation value is calculated based on the desquamation rate. For example, the rough skin evaluation value is calculated using the following equation.
Rough skin evaluation value = 22.4 × (desquamation ratio) − 2.51 (Formula 1)
In the area variance value calculation step (S84), the variance value of the area of the desquamating region is calculated with reference to the desquamation region area table.
In the area dispersion value evaluation step (S85), the rough skin evaluation value is calculated from the dispersion value calculated in step (S84). For example, the rough skin evaluation value is calculated using the following equation.
Rough skin evaluation value = 0.0377 × (dispersion value) +0.502 (Expression 2)
As described in the example section, the evaluation formula for obtaining such a rough skin evaluation value is derived in advance from the sample skin image as a correlation formula between the subjective evaluation score of the rough skin state, the desquamation rate, and the variance value, and the correlation What is necessary is just to produce | generate beforehand from a type | formula.
Thus, in the present embodiment, one of the different indicators is the desquamation ratio, and the other is the variance value of the area of the desquamation area, that is, the degree of variation in the area of the desquamation area. In this embodiment, the index given to one of the different formulas is the desquamation rate, and the index given to the other formula is the variance value, that is, the degree of variation in the area of the desquamation area.
Indicators other than those listed here can be used as appropriate, and the form of the correlation expression can be a higher-order expression or other form of function as long as it can approximate the subjective evaluation score. Of course.

The skin image obtained by imaging the skin of the subject S is displayed on the touch panel 34 connected to the information processing apparatus 33 together with the rough skin evaluation value, the desquamation ratio, the area dispersion value of the desquamation area, etc. calculated in step (S54). Is done.
In this way, the state of desquamation in the skin is quantified (area dispersion value, desquamation ratio, etc.), and the skin condition is better understood by the quantified desquamation state evaluation (skin roughness evaluation value). As a result, the hope for skin care can be increased or the care to be applied can be changed. For example, by installing the skin diagnosis system 30 in a beauty salon and quantifying the skin condition and showing it to the subject, the need for care is better understood. In addition, for the practitioner, they can be used as an index for determining different care methods, such as changing the amount of cosmetics used according to the amount of desquamation and the dispersion value or changing the degree of massage.

[Modification]
The rough skin evaluation based on the area information of the desquamation area is not limited to the determination method of the present embodiment described above, and for example, the following determination method may be used.

FIG. 9 is a flowchart showing a first modification of the rough skin evaluation determination step (S54).
Also in the first modified example, first, a desquamation ratio is calculated (step (S91)).
Next, an area variance value calculation step (S92) is executed. The area variance calculation step (S92) is the same as the above-described step (S84).
Subsequently, in step (S93), it is determined whether the desquamation ratio is equal to or greater than a predetermined ratio (0.18%). When the desquamation ratio is equal to or greater than the predetermined ratio (0.18%) (S93; Y), the area dispersion value evaluation 1 step (S94) is executed, and when the desquamation ratio is less than the predetermined ratio (S93; N), the area The variance value evaluation 2 step (S95) is executed.

The area dispersion value evaluation 1 step (S94) and the area dispersion value evaluation 2 step (S95) both use the area dispersion value of the desquamation area, but the evaluation formulas are different.
In the area dispersion value evaluation 1 step (S94), the following (Expression 3) is used, and in the area dispersion value evaluation 2 step (S95), the following (Expression 4) is used.
Skin roughness evaluation value = 0.04 × (dispersion value) +0.876 (Expression 3)
Rough skin evaluation value = 0.0377 × (dispersion value) +0.502 (Expression 4)
In this manner, the rough skin state can be quantified using the same index and different formulas depending on whether the desquamation ratio is lower or higher than the predetermined ratio. In the first modification, the index given to each different formula is the variance value of the area of the desquamation area.
Even in this way, the appearance of rough skin can be quantified with high accuracy.
Further, in the rough skin evaluation determination step shown in FIGS. 8 and 9, the variance value of the area of the desquamation region is used as the degree of variation in the area of the desquamation region, but instead of the variance value, the standard of the area of the desquamation region is used. Other variation indices such as a deviation value, a coefficient of variation (a value obtained by dividing a variance value by an average value) may be used.

FIG. 10 is a flowchart showing a second modification of the rough skin evaluation determination step (S54).
Also in the second modified example, first, a desquamation ratio is calculated (step (S101)).
Subsequently, in step (S102), it is determined whether the desquamation rate is equal to or greater than a predetermined rate (0.18%). When the desquamation rate is a predetermined rate (0.18%) or more (S102; Y), the desquamation rate evaluation 1 step (S103) is executed, and when the desquamation rate is less than the predetermined rate (S102; N), the desquamation rate. Evaluation 2 step (S104) is executed.

Both the desquam rate evaluation 1 step (S103) and the desquam rate evaluation 2 step (S104) use the desquam rate, but their evaluation formulas are different.
The following (Formula 5) is used in the step 1 for evaluating the desquamation ratio (S103), and the following (Formula 6) is used in the step 2 for evaluating the desquamation ratio (S104).
Rough skin evaluation value = 21.7 × (desquamation ratio) − 0.78 (Formula 5)
Evaluation value for rough skin = 22.4 × (desquamation ratio) − 2.51 (Expression 6)
In the second modified example, similarly to the first modified example, the rough skin state can be quantified by using the same index and different formulas depending on whether the desquamation ratio is lower or higher than the predetermined ratio. In the second modification, the index given to each different formula is the desquamation ratio, and the degree of variation in the area of the desquamation area is not used.
Even in this way, the appearance of rough skin can be quantified with high accuracy.

According to the present inventors, the value obtained by multiplying the degree of variation in the area of the desquamating region by another index value relating to the area of the desquamating region is an evaluation value when a human visually evaluates the rough skin state. It has been found that there is a higher correlation. Therefore, instead of the above-mentioned dispersion value, a value obtained by multiplying the average area, intermediate area, or most frequent area of the desquamation area, or the desquamation ratio and the degree of variation in the area of the desquamation area (the above-described dispersion value, etc.). May be used. When obtaining the most frequent area, areas that are approximated within a predetermined range may be grouped.
In this case, the step of obtaining the average area, the intermediate area, or the most frequent area of the desquamating region with reference to the desquamating region area table may be executed before or after steps (S84) and (S92) or simultaneously with them. Then, an index given to one of the different indexes or at least one of the different formulas is set as the multiplied value. Specifically, instead of the dispersion values of (Equation 2), (Equation 3), and (Equation 4), the average area, intermediate area, or most frequent area of the desquamation area, or the desquamation ratio, A value obtained by multiplying the degree of variation in area (such as the above-described dispersion value) is used.
In this way, the appearance of rough skin can be quantified with higher accuracy.

Moreover, the extraction of the desquamation area | region of the process (S11) shown by FIG. 1 may not be the method of step (S51) and (S52) shown by FIG. 5, and the part which desquashed from the image which image | photographed the skin is continuous. Various shooting methods and image processing methods can be adopted that are selected as the selected region.
As a method for calculating the area of each desquamating region, a known calculation method such as a method of approximating the shape, circumference, or other parameters can be used in addition to the method of counting the number of pixels.
Moreover, in order to raise a precision more, the number of the predetermined ratio compared with a desquamation ratio may be increased, and a rough skin evaluation value may be calculated by three or more evaluation formulas. In this case, for example, the rough skin evaluation value may be calculated based on the desquamation ratio at a predetermined desquamation ratio.

The information processing apparatus 33 that executes the above-described rough skin evaluation method may include the acquisition unit 21 and the quantification unit 22 illustrated in FIG.
In addition to the above desquamation ratio, the acquisition unit 21 may further acquire the degree of variation in the area of the desquamation area in the skin image of the subject, or the average area, intermediate area, or mode of the desquamation area in the skin image. You may further acquire the value which multiplied the area and the variation degree of the area of the desquamation area | region in the said skin image. For example, the acquisition unit 21 executes Step (S84) or Step (S92).
The quantification unit 22 may use the desquamation ratio, the degree of variation in the area of the desquamation region, or the multiplied value as an index given to one of the different indices or at least one of the different methods. For example, the quantification unit 22 executes steps (S83), (S85), (S94), (S95), (S103), or (S104). For example, when calculating the rough skin evaluation value as described above, the quantification unit 22 holds (Formula 1) described above in advance.

  The term “quantification” as used in the present specification means not only to quantify by calculation, but also to make a state a value by applying it to a comparison table and digitizing. In addition, “quantification” includes not only showing the obtained value as a numerical value but also changing the display on the screen according to the value or obtaining a value to change the sound generated by the acoustic device.

  Examples will be given below to describe the above-described embodiment in more detail. The present invention is not limited in any way by the following examples. The following example demonstrates the effectiveness of quantifying the appearance of rough skin in the above-described embodiment.

In this example, 24 SP polarized images obtained by imaging the left cheeks of 24 subjects were used as sample skin images, and the desquamation state of each sample skin image was evaluated by five experts. In this evaluation, for each sample skin image, the degree of conspicuousness of desquamation is scored in 7 stages from 1 point to 4 points in 0.5 points, and the average score of 5 experts is the desquamation of the sample skin image. It was given as a visual score.
On the other hand, the above-described steps (S51), (S52), and (S53) are applied to each sample skin image (SP polarization image), and the area for each desquamation region is calculated for each sample skin image. . And about each sample skin image, the average area of the desquamation area | region, the variance value of an area, the variation coefficient (value which divided the dispersion value by the average value), and the desquamation ratio were calculated, respectively.

FIG. 11 is a graph showing the correlation between the variance value of the area of the desquamation area and the desquamation visual score, and FIG. 12 is a graph showing the correlation between the variation coefficient of the area of the desquamation area and the desquamation visual score.
11 and 12, the determination coefficients (R ² ) are 0.408 and 0.2183. Therefore, according to the graphs of FIGS. 11 and 12, the variance value and the variation coefficient of the area of the desquamating region are It can be seen that both show some degree of correlation with the desquamation visual score. Here, the variance value and the coefficient of variation are both values indicating the degree of variation in the area of the desquamation area, and the desquamation visual score is a value indicating the appearance of the subject's rough skin (result of subjective evaluation). From this result, it is clear that the degree of variation in the area of the desquamation area correlates with the evaluation score of the appearance of the subject's rough skin.

FIG. 13 is a graph showing a correlation between a value obtained by multiplying the variance value of the area of the desquamation area by the average area of the desquamation area and the desquamation visual score, and FIG. It is a graph which shows the correlation with the value which multiplied and desquamation visual score.
In FIGS. 13 and 14, since the determination coefficient (R ² ) is 0.4303 and 0.545, according to the graphs of FIGS. 13 and 14, the variance value of the area of the debris region and the debris region It can be seen that both the value obtained by multiplying the average area and the value obtained by multiplying the dispersion value and the desquamation rate show a high correlation with the desquamation visual score. Further, these multiplied values show a higher correlation with the evaluation score than the degree of variation in the area of the desquamating region shown in FIGS. 11 and 12 alone. In addition, the desquamation ratio of each graph is shown by a decimal (ratio).
In this way, the value obtained by multiplying the degree of variation in the area of the desquamation area by other index values regarding the area of the desquamation area (average area, intermediate area, most frequent area, desquamation ratio, etc.) It is demonstrated to be more highly correlated with the impression evaluation score.

FIG. 15 is a graph showing a correlation between a desquamation ratio and a desquamation visual score.
Since the determination coefficient (R ² ) is 0.5446, according to the graph of FIG. 15, it is recognized that the desquamation ratio also shows a high correlation with the desquamation visual score. In addition, the desquamation ratio of FIG. 15 is shown by the decimal (ratio).
Here, the present inventors further show a correlation different from the desquamation visual score between the group of sample skin images having a desquamation ratio (ratio) of 0.18% or more and the other group of sample skin images. I realized that it might be. Therefore, as shown in FIGS. 16 and 17, the sample skin images were grouped with a desquamation rate of 0.18%, and the correlation with the desquamation visual score was confirmed for the divided subset.

FIG. 16A is a graph showing the correlation between the desquamation visual score and the variance value of the area of the desquamation area regarding the sample skin image with a desquamation ratio (ratio) of less than 0.18%, and FIG. It is a graph which shows the correlation with a desquamation visual score and a desquamation rate regarding the sample skin image whose desquamation rate (ratio) is less than 0.18%.
In FIGS. 16A and 16B, the coefficient of determination (R ² ) of the correlation formula between the variance value of the area of the desquamation area and the desquamation visual score is 0.473, and the correlation formula between the desquamation ratio and the desquamation visual score. The determination coefficient (R ² ) is 0.461. Therefore, according to FIGS. 16A and 16B, in the sample skin image with a desquamation rate (ratio) of less than 0.18%, the variance value of the area of the desquamation area correlates with the desquamation visual score rather than the desquamation rate. Is found to be high.

FIG. 17 (a) is a graph showing the correlation between the desquamation visual score and the variance value of the area of the desquamation area for a sample skin image with a desquamation ratio (ratio) of 0.18% or more, and FIG. It is a graph which shows the correlation with a desquamation visual score and a desquamation rate regarding the sample skin image whose desquamation rate (ratio) is 0.18% or more.
In FIGS. 17A and 17B, the coefficient of determination (R ² ) of the correlation formula between the variance value of the area of the desquamation area and the desquamation visual score is 0.4785, and the correlation formula between the desquamation ratio and the desquamation visual score. The determination coefficient (R ² ) is 0.5708. Therefore, according to FIGS. 17A and 17B, in the sample skin image with the desquamation ratio (ratio) of 0.18% or more, the desquamation ratio is more correlated with the desquamation visual score than the dispersion value. It is recognized that it is expensive.

  According to FIGS. 16 (a) and 16 (b) and FIGS. 17 (a) and 17 (b), when the percentage of desquamation falls below a predetermined percentage (0.18%), the degree of variation in the area of the desquamation area (dispersion value, etc.) ) Is quantified, and when the desquamation ratio exceeds a predetermined ratio (0.18%), it can be seen that it is desirable to quantify the rough skin condition using the desquamation ratio. However, the predetermined ratio is not limited to 0.18% in the present embodiment. The predetermined ratio may vary depending on the rough skin state of the sample skin image. In addition, instead of the degree of variation in the area of the desquamating region, a value obtained by multiplying the degree of variation and other index values related to the area of the desquamating region (average area, intermediate area, most frequent area, desquamation ratio, etc.) is used May be.

  Part or all of the above-described embodiments and modifications may be specified as follows. However, the above-described embodiment and modification examples are not limited to the following description.

<1> a step of obtaining a desquamation ratio, which is a ratio of the area of the desquamation region extracted from the skin image to the skin area of the subject's skin image;
Quantifying the rough skin condition using a different index or a different method depending on whether the acquired desquamation ratio is lower than a predetermined ratio or higher.
A rough skin evaluation method.

<2> One of the different indicators or an indicator given to at least one of the different methods is the desquamation ratio.
<1> The rough skin evaluation method according to <1>.
<3> A step of obtaining the degree of variation in the area of the desquamation region in the skin image,
Further including
The index given to one of the different indexes or at least one of the different methods is the obtained degree of variation.
<1> or the rough skin evaluation method according to <2>.
<4> A step of obtaining a value obtained by multiplying the average area, intermediate area, or most frequent area of the desquamating region in the skin image by the degree of variation in the area of the desquamating region in the skin image,
Further including
The indicator given to one of the different indicators or at least one of the different methods is the multiplied value,
<1> or the rough skin evaluation method according to <2>.
<5> Acquisition means for acquiring a desquamation ratio, which is a ratio of the area of the desquamation area extracted from the skin image to the skin area of the subject's skin image;
Quantifying means for quantifying the rough skin condition using different indicators or different methods depending on whether the acquired desquamation ratio is below or above a predetermined ratio;
An apparatus for evaluating rough skin.
<6> The quantification means uses the desquamation ratio as an index given to one of the different indexes or at least one of the different methods.
<5> The rough skin evaluation apparatus according to <5>.
<7> The acquisition unit further acquires the degree of variation in the area of the desquamating region in the skin image,
The quantification unit uses the obtained degree of variation as an index given to one of the different indexes or at least one of the different methods.
The rough skin evaluation apparatus as described in <5> or <6>.
<8> The acquisition unit further acquires a value obtained by multiplying the average area, intermediate area, or most frequent area of the desquamating region in the skin image by the variation degree of the area of the desquamating region in the skin image,
The quantification means uses the multiplied value as an index given to one of the different indexes or at least one of the different methods.
The rough skin evaluation apparatus as described in <5> or <6>.

10 rough skin evaluation device 11 CPU
12 Memory 13 Input / output I / F
14 Communication unit 15 Output device 16 Input device 21 Acquisition unit 22 Quantification unit 30 Skin diagnosis system 31 Imaging device 32 Projector 33 Information processing device 34 Touch panel 36 Polarizing filter for imaging

Claims (8)

Obtaining a desquamation ratio that is a ratio of the area of the desquamation region extracted from the skin image to the skin area of the skin image of the subject;
Quantifying the rough skin condition using a different index or a different method depending on whether the acquired desquamation ratio is lower than a predetermined ratio or higher.
A rough skin evaluation method. The indicator given to one of the different indicators or at least one of the different methods is the desquamation rate,
The rough skin evaluation method of Claim 1. Obtaining a degree of variation in the area of the desquamation area in the skin image;
Further including
The index given to one of the different indexes or at least one of the different methods is the obtained degree of variation.
The rough skin evaluation method according to claim 1 or 2. Obtaining a value obtained by multiplying the average area, intermediate area, or most frequent area of the desquamation region in the skin image by the degree of variation in the area of the desquamation region in the skin image;
Further including
The indicator given to one of the different indicators or at least one of the different methods is the multiplied value,
The rough skin evaluation method according to claim 1 or 2. An acquisition means for acquiring a desquamation ratio, which is a ratio of an area of a desquamation area extracted from the skin image to a skin area of a subject's skin image;
Quantifying means for quantifying the rough skin condition using different indicators or different methods depending on whether the acquired desquamation ratio is below or above a predetermined ratio;
An apparatus for evaluating rough skin. The quantification means uses the desquamation ratio as an index given to one of the different indexes or at least one of the different methods.
The rough skin evaluation apparatus according to claim 5. The acquisition means further acquires the degree of variation in the area of the desquamating region in the skin image,
The quantification unit uses the obtained degree of variation as an index given to one of the different indexes or at least one of the different methods.
The rough skin evaluation apparatus according to claim 5 or 6. The obtaining means further obtains a value obtained by multiplying the average area, intermediate area, or most frequent area of the desquamating area in the skin image by the degree of variation in the area of the desquamation area in the skin image,
The quantification means uses the multiplied value as an index given to one of the different indexes or at least one of the different methods.
The rough skin evaluation apparatus according to claim 5 or 6.

Images